{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MACTQGW3VXGXXQ2XRDRIJC7XEO","short_pith_number":"pith:MACTQGW3","schema_version":"1.0","canonical_sha256":"6005381adbadcd7bc35788e2848bf7238d7b9757274291bb0dd1edcda5522f9b","source":{"kind":"arxiv","id":"2303.02868","version":1},"attestation_state":"computed","paper":{"title":"Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Dian Jiao, Fangcheng Fu, Jinbao Xue, Xiaonan Nie, Xupeng Miao, Yangyu Tao, Yi Liu","submitted_at":"2023-03-06T03:36:26Z","abstract_excerpt":"Recent years have witnessed the unprecedented achievements of large-scale pre-trained models, especially the Transformer models. Many products and services in Tencent Inc., such as WeChat, QQ, and Tencent Advertisement, have been opted in to gain the power of pre-trained models. In this work, we present Angel-PTM, a productive deep learning system designed for pre-training and fine-tuning Transformer models. Angel-PTM can train extremely large-scale models with hierarchical memory efficiently. The key designs of Angel-PTM are the fine-grained memory management via the Page abstraction and a un"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.02868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T03:36:26Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"82e8e6f3b244e9d1a940eeab1c8967f63261e229720110037b107ec759406aaa","abstract_canon_sha256":"4affa89d101dcd8506c01001833907cd6b8b6e0e349498da60431bff212deb78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:16.295610Z","signature_b64":"t6USeiXcuLEEeJ47gCP6SmYhSRdlW/UHpbo5v1rS5C8BiWIM/VRHexlx+z/TblgN86YA/KeMHUsBTroa+aouCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6005381adbadcd7bc35788e2848bf7238d7b9757274291bb0dd1edcda5522f9b","last_reissued_at":"2026-07-05T05:48:16.295113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:16.295113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Dian Jiao, Fangcheng Fu, Jinbao Xue, Xiaonan Nie, Xupeng Miao, Yangyu Tao, Yi Liu","submitted_at":"2023-03-06T03:36:26Z","abstract_excerpt":"Recent years have witnessed the unprecedented achievements of large-scale pre-trained models, especially the Transformer models. Many products and services in Tencent Inc., such as WeChat, QQ, and Tencent Advertisement, have been opted in to gain the power of pre-trained models. In this work, we present Angel-PTM, a productive deep learning system designed for pre-training and fine-tuning Transformer models. Angel-PTM can train extremely large-scale models with hierarchical memory efficiently. The key designs of Angel-PTM are the fine-grained memory management via the Page abstraction and a un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02868","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.02868/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.02868","created_at":"2026-07-05T05:48:16.295170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02868v1","created_at":"2026-07-05T05:48:16.295170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02868","created_at":"2026-07-05T05:48:16.295170+00:00"},{"alias_kind":"pith_short_12","alias_value":"MACTQGW3VXGX","created_at":"2026-07-05T05:48:16.295170+00:00"},{"alias_kind":"pith_short_16","alias_value":"MACTQGW3VXGXXQ2X","created_at":"2026-07-05T05:48:16.295170+00:00"},{"alias_kind":"pith_short_8","alias_value":"MACTQGW3","created_at":"2026-07-05T05:48:16.295170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04976","citing_title":"Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO","json":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO.json","graph_json":"https://pith.science/api/pith-number/MACTQGW3VXGXXQ2XRDRIJC7XEO/graph.json","events_json":"https://pith.science/api/pith-number/MACTQGW3VXGXXQ2XRDRIJC7XEO/events.json","paper":"https://pith.science/paper/MACTQGW3"},"agent_actions":{"view_html":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO","download_json":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO.json","view_paper":"https://pith.science/paper/MACTQGW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02868&json=true","fetch_graph":"https://pith.science/api/pith-number/MACTQGW3VXGXXQ2XRDRIJC7XEO/graph.json","fetch_events":"https://pith.science/api/pith-number/MACTQGW3VXGXXQ2XRDRIJC7XEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO/action/storage_attestation","attest_author":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO/action/author_attestation","sign_citation":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO/action/citation_signature","submit_replication":"https://pith.science/pith/MACTQGW3VXGXXQ2XRDRIJC7XEO/action/replication_record"}},"created_at":"2026-07-05T05:48:16.295170+00:00","updated_at":"2026-07-05T05:48:16.295170+00:00"}